A cascaded deep learning framework for photovoltaic power forecasting with multi-fidelity inputs

Luo，Xing1; Zhang，Dongxiao1,2

2023-04-01

10.1016/j.energy.2023.126636

ENERGY   影响因子和分区

0360-5442

1873-6785

Accurate forecasts of photovoltaic power (PVP) are essential to the production, transmission, and distribution of electricity in power systems. However, PVP output is strongly weather-dependent, and the forecasting of PVP is highly dependent on the quality of numerical weather prediction (NWP) data. In recent years, a huge volume of numerical weather observation (NWO) data which are strongly associated with PVP output have been collected on-site by widely-installed smart meters and sensors. Appropriately utilizing high-fidelity NWO, in addition to low-fidelity NWP, has great potential in promoting the forecasting capability of deep learning (DL) models. Therefore, this paper proposes a cascaded multi-fidelity deep learning (CMF-DL) framework, which is coordinately driven by the data of both NWO and NWP, to deal with the day-ahead PVP forecasting problem. The proposed CMF-DL framework possesses great compatibility, and thus it can be incorporated with various DL models, such as the long short-term memory (LSTM) model and the gated recurrent unit (GRU) model. Subsequently, incorporated with CMF-DL, two newly-developed forecasting models, i.e., CMF-LSTM and CMF-GRU, are proposed, and datasets from a real-life PV plant are utilized, to evaluate the feasibility and effectiveness of the proposed approaches. From the results, the proposed CMF-LSTM and CMF-GRU show greater forecasting capability and anti-noise ability than the basic LSTM and GRU. Both CMF-LSTM and CMF-GRU can accept noisy NWP data with up to 35% errors. Additionally, compared to the persistence model, the forecasting skills of CMF-LSTM and CMF-GRU can be significantly promoted by 39.87% and 44.02%, respectively. The proposed CMF-LSTM and CMF-GRU also achieve better day-ahead PVP forecasting performance than the widely-used reference models in previous works.

Deep learning Multi-fidelity inputs Numerical weather observation Numerical weather prediction Photovoltaic power forecasting

SCI ; EI

英语

通讯

Thermodynamics ; Energy & Fuels

Thermodynamics ; Energy & Fuels

WOS:000993981500001

PERGAMON-ELSEVIER SCIENCE LTD

20230213381166

Electric power transmission ; Power quality ; Weather forecasting

Meteorology:443 ; Electric Power Transmission:706.1.1 ; Electric Power Distribution:706.1.2

ENGINEERING

2-s2.0-85146070151

Scopus

1.Department of Mathematics and Theories,Peng Cheng Laboratory,Shenzhen,Guangdong,518055,China
2.National Center for Applied Mathematics Shenzhen (NCAMS),Southern University of Science and Technology,Shenzhen,Guangdong,518055,China

Luo，Xing,Zhang，Dongxiao. A cascaded deep learning framework for photovoltaic power forecasting with multi-fidelity inputs[J]. ENERGY,2023,268.

Luo，Xing,&Zhang，Dongxiao.(2023).A cascaded deep learning framework for photovoltaic power forecasting with multi-fidelity inputs.ENERGY,268.

Luo，Xing,et al."A cascaded deep learning framework for photovoltaic power forecasting with multi-fidelity inputs".ENERGY 268(2023).